Compare commits

..

4 Commits

Author SHA1 Message Date
Clément Renault
0b4f635817 WIP missing DeCboRoaringBitmapCodec::bytes_encode implem 2025-11-24 18:22:57 +01:00
Kerollmops
a558dbdfde Remove the unwraps, asserts and return actual io errors 2025-11-24 13:41:37 +01:00
Kerollmops
952b8b85eb Move to a two bytes header 2025-11-24 13:41:37 +01:00
Kerollmops
82a260fec8 Introduce a first working version of the DeBitmapCodec 2025-11-24 13:41:37 +01:00
25 changed files with 567 additions and 51 deletions

57
Cargo.lock generated
View File

@@ -584,7 +584,7 @@ source = "git+https://github.com/meilisearch/bbqueue#cbb87cc707b5af415ef203bdaf2
[[package]]
name = "benchmarks"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"anyhow",
"bumpalo",
@@ -794,7 +794,7 @@ dependencies = [
[[package]]
name = "build-info"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"anyhow",
"time",
@@ -1784,7 +1784,7 @@ dependencies = [
[[package]]
name = "dump"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"anyhow",
"big_s",
@@ -1964,6 +1964,16 @@ dependencies = [
"syn 2.0.106",
]
[[package]]
name = "env_logger"
version = "0.8.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a19187fea3ac7e84da7dacf48de0c45d63c6a76f9490dae389aead16c243fce3"
dependencies = [
"log",
"regex",
]
[[package]]
name = "equivalent"
version = "1.0.2"
@@ -2027,7 +2037,7 @@ checksum = "37909eebbb50d72f9059c3b6d82c0463f2ff062c9e95845c43a6c9c0355411be"
[[package]]
name = "file-store"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"tempfile",
"thiserror 2.0.16",
@@ -2049,7 +2059,7 @@ dependencies = [
[[package]]
name = "filter-parser"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"insta",
"levenshtein_automata",
@@ -2077,7 +2087,7 @@ dependencies = [
[[package]]
name = "flatten-serde-json"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"criterion",
"serde_json",
@@ -2234,7 +2244,7 @@ dependencies = [
[[package]]
name = "fuzzers"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"arbitrary",
"bumpalo",
@@ -3188,7 +3198,7 @@ dependencies = [
[[package]]
name = "index-scheduler"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"anyhow",
"backoff",
@@ -3461,7 +3471,7 @@ dependencies = [
[[package]]
name = "json-depth-checker"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"criterion",
"serde_json",
@@ -3980,7 +3990,7 @@ checksum = "490cc448043f947bae3cbee9c203358d62dbee0db12107a74be5c30ccfd09771"
[[package]]
name = "meili-snap"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"insta",
"md5",
@@ -3991,7 +4001,7 @@ dependencies = [
[[package]]
name = "meilisearch"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"actix-cors",
"actix-http",
@@ -4088,7 +4098,7 @@ dependencies = [
[[package]]
name = "meilisearch-auth"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"base64 0.22.1",
"enum-iterator",
@@ -4107,7 +4117,7 @@ dependencies = [
[[package]]
name = "meilisearch-types"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"actix-web",
"anyhow",
@@ -4142,7 +4152,7 @@ dependencies = [
[[package]]
name = "meilitool"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"anyhow",
"clap",
@@ -4176,13 +4186,14 @@ dependencies = [
[[package]]
name = "milli"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"arroy",
"bbqueue",
"big_s",
"bimap",
"bincode 1.3.3",
"bitpacking",
"bstr",
"bumpalo",
"bumparaw-collections",
@@ -4229,6 +4240,7 @@ dependencies = [
"obkv",
"once_cell",
"ordered-float 5.0.0",
"quickcheck",
"rand 0.8.5",
"rayon",
"rhai",
@@ -4757,7 +4769,7 @@ checksum = "9b4f627cb1b25917193a259e49bdad08f671f8d9708acfd5fe0a8c1455d87220"
[[package]]
name = "permissive-json-pointer"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"big_s",
"serde_json",
@@ -5171,6 +5183,17 @@ dependencies = [
"serde",
]
[[package]]
name = "quickcheck"
version = "1.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "588f6378e4dd99458b60ec275b4477add41ce4fa9f64dcba6f15adccb19b50d6"
dependencies = [
"env_logger",
"log",
"rand 0.8.5",
]
[[package]]
name = "quinn"
version = "0.11.9"
@@ -7879,7 +7902,7 @@ dependencies = [
[[package]]
name = "xtask"
version = "1.27.0"
version = "1.26.0"
dependencies = [
"anyhow",
"build-info",

View File

@@ -23,7 +23,7 @@ members = [
]
[workspace.package]
version = "1.27.0"
version = "1.26.0"
authors = [
"Quentin de Quelen <quentin@dequelen.me>",
"Clément Renault <clement@meilisearch.com>",

View File

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 27, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
1 {uid: 1, batch_uid: 1, status: succeeded, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
2 {uid: 2, batch_uid: 2, status: succeeded, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
3 {uid: 3, batch_uid: 3, status: failed, error: ResponseError { code: 200, message: "Index `doggo` already exists.", error_code: "index_already_exists", error_type: "invalid_request", error_link: "https://docs.meilisearch.com/errors#index_already_exists" }, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
@@ -57,7 +57,7 @@ girafo: { number_of_documents: 0, field_distribution: {} }
[timestamp] [4,]
----------------------------------------------------------------------
### All Batches:
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.27.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.26.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
1 {uid: 1, details: {"primaryKey":"mouse"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"catto":1}}, stop reason: "created batch containing only task with id 1 of type `indexCreation` that cannot be batched with any other task.", }
2 {uid: 2, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 2 of type `indexCreation` that cannot be batched with any other task.", }
3 {uid: 3, details: {"primaryKey":"bone"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"indexCreation":1},"indexUids":{"doggo":1}}, stop reason: "created batch containing only task with id 3 of type `indexCreation` that cannot be batched with any other task.", }

View File

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 27, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
----------------------------------------------------------------------
### Status:
enqueued [0,]

View File

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 27, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
0 {uid: 0, status: enqueued, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
----------------------------------------------------------------------
### Status:

View File

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 27, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
----------------------------------------------------------------------
### Status:
@@ -37,7 +37,7 @@ catto [1,]
[timestamp] [0,]
----------------------------------------------------------------------
### All Batches:
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.27.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.26.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
----------------------------------------------------------------------
### Batch to tasks mapping:
0 [0,]

View File

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 27, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
0 {uid: 0, batch_uid: 0, status: failed, error: ResponseError { code: 200, message: "Planned failure for tests.", error_code: "internal", error_type: "internal", error_link: "https://docs.meilisearch.com/errors#internal" }, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
2 {uid: 2, status: enqueued, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
----------------------------------------------------------------------
@@ -40,7 +40,7 @@ doggo [2,]
[timestamp] [0,]
----------------------------------------------------------------------
### All Batches:
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.27.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.26.0"}, stats: {"totalNbTasks":1,"status":{"failed":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
----------------------------------------------------------------------
### Batch to tasks mapping:
0 [0,]

View File

@@ -6,7 +6,7 @@ source: crates/index-scheduler/src/scheduler/test_failure.rs
[]
----------------------------------------------------------------------
### All Tasks:
0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 27, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
0 {uid: 0, batch_uid: 0, status: succeeded, details: { from: (1, 12, 0), to: (1, 26, 0) }, kind: UpgradeDatabase { from: (1, 12, 0) }}
1 {uid: 1, status: enqueued, details: { primary_key: Some("mouse"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "catto", primary_key: Some("mouse") }}
2 {uid: 2, status: enqueued, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
3 {uid: 3, status: enqueued, details: { primary_key: Some("bone"), old_new_uid: None, new_index_uid: None }, kind: IndexCreation { index_uid: "doggo", primary_key: Some("bone") }}
@@ -43,7 +43,7 @@ doggo [2,3,]
[timestamp] [0,]
----------------------------------------------------------------------
### All Batches:
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.27.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
0 {uid: 0, details: {"upgradeFrom":"v1.12.0","upgradeTo":"v1.26.0"}, stats: {"totalNbTasks":1,"status":{"succeeded":1},"types":{"upgradeDatabase":1},"indexUids":{}}, stop reason: "stopped after the last task of type `upgradeDatabase` because they cannot be batched with tasks of any other type.", }
----------------------------------------------------------------------
### Batch to tasks mapping:
0 [0,]

View File

@@ -50,7 +50,6 @@ pub fn upgrade_index_scheduler(
(1, 24, _) => 0,
(1, 25, _) => 0,
(1, 26, _) => 0,
(1, 27, _) => 0,
(major, minor, patch) => {
if major > current_major
|| (major == current_major && minor > current_minor)

View File

@@ -43,7 +43,7 @@ async fn version_too_old() {
std::fs::write(db_path.join("VERSION"), "1.11.9999").unwrap();
let options = Opt { experimental_dumpless_upgrade: true, ..default_settings };
let err = Server::new_with_options(options).await.map(|_| ()).unwrap_err();
snapshot!(err, @"Database version 1.11.9999 is too old for the experimental dumpless upgrade feature. Please generate a dump using the v1.11.9999 and import it in the v1.27.0");
snapshot!(err, @"Database version 1.11.9999 is too old for the experimental dumpless upgrade feature. Please generate a dump using the v1.11.9999 and import it in the v1.26.0");
}
#[actix_rt::test]
@@ -58,7 +58,7 @@ async fn version_requires_downgrade() {
std::fs::write(db_path.join("VERSION"), format!("{major}.{minor}.{patch}")).unwrap();
let options = Opt { experimental_dumpless_upgrade: true, ..default_settings };
let err = Server::new_with_options(options).await.map(|_| ()).unwrap_err();
snapshot!(err, @"Database version 1.27.1 is higher than the Meilisearch version 1.27.0. Downgrade is not supported");
snapshot!(err, @"Database version 1.26.1 is higher than the Meilisearch version 1.26.0. Downgrade is not supported");
}
#[actix_rt::test]

View File

@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
"progress": null,
"details": {
"upgradeFrom": "v1.12.0",
"upgradeTo": "v1.27.0"
"upgradeTo": "v1.26.0"
},
"stats": {
"totalNbTasks": 1,

View File

@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
"progress": null,
"details": {
"upgradeFrom": "v1.12.0",
"upgradeTo": "v1.27.0"
"upgradeTo": "v1.26.0"
},
"stats": {
"totalNbTasks": 1,

View File

@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
"progress": null,
"details": {
"upgradeFrom": "v1.12.0",
"upgradeTo": "v1.27.0"
"upgradeTo": "v1.26.0"
},
"stats": {
"totalNbTasks": 1,

View File

@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
"canceledBy": null,
"details": {
"upgradeFrom": "v1.12.0",
"upgradeTo": "v1.27.0"
"upgradeTo": "v1.26.0"
},
"error": null,
"duration": "[duration]",

View File

@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
"canceledBy": null,
"details": {
"upgradeFrom": "v1.12.0",
"upgradeTo": "v1.27.0"
"upgradeTo": "v1.26.0"
},
"error": null,
"duration": "[duration]",

View File

@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
"canceledBy": null,
"details": {
"upgradeFrom": "v1.12.0",
"upgradeTo": "v1.27.0"
"upgradeTo": "v1.26.0"
},
"error": null,
"duration": "[duration]",

View File

@@ -8,7 +8,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
"progress": null,
"details": {
"upgradeFrom": "v1.12.0",
"upgradeTo": "v1.27.0"
"upgradeTo": "v1.26.0"
},
"stats": {
"totalNbTasks": 1,

View File

@@ -12,7 +12,7 @@ source: crates/meilisearch/tests/upgrade/v1_12/v1_12_0.rs
"canceledBy": null,
"details": {
"upgradeFrom": "v1.12.0",
"upgradeTo": "v1.27.0"
"upgradeTo": "v1.26.0"
},
"error": null,
"duration": "[duration]",

View File

@@ -120,14 +120,16 @@ twox-hash = { version = "2.1.1", default-features = false, features = [
] }
geo-types = "0.7.16"
zerometry = "0.3.0"
bitpacking = "0.9.2"
[dev-dependencies]
mimalloc = { version = "0.1.47", default-features = false }
# fixed version due to format breakages in v1.40
insta = "=1.39.0"
mimalloc = { version = "0.1.47", default-features = false }
maplit = "1.0.2"
md5 = "0.7.0"
meili-snap = { path = "../meili-snap" }
quickcheck = "1.0.3"
rand = { version = "0.8.5", features = ["small_rng"] }
[features]

View File

@@ -22,7 +22,9 @@ pub use self::beu32_str_codec::BEU32StrCodec;
pub use self::field_id_word_count_codec::FieldIdWordCountCodec;
pub use self::fst_set_codec::FstSetCodec;
pub use self::obkv_codec::ObkvCodec;
pub use self::roaring_bitmap::{BoRoaringBitmapCodec, CboRoaringBitmapCodec, RoaringBitmapCodec};
pub use self::roaring_bitmap::{
BoRoaringBitmapCodec, CboRoaringBitmapCodec, DeCboRoaringBitmapCodec, RoaringBitmapCodec,
};
pub use self::roaring_bitmap_length::{
BoRoaringBitmapLenCodec, CboRoaringBitmapLenCodec, RoaringBitmapLenCodec,
};

View File

@@ -19,8 +19,19 @@ pub const THRESHOLD: usize = 7;
pub struct CboRoaringBitmapCodec;
impl CboRoaringBitmapCodec {
/// If the number of items (u32s) to encode is less than or equal to the threshold
/// it means that it would weigh the same or less than the RoaringBitmap
/// header, so we directly encode them using ByteOrder instead.
pub fn bitmap_serialize_as_raw_u32s(roaring: &RoaringBitmap) -> bool {
roaring.len() <= THRESHOLD as u64
}
pub fn bytes_deserialize_as_raw_u32s(bytes: &[u8]) -> bool {
bytes.len() <= THRESHOLD * size_of::<u32>()
}
pub fn serialized_size(roaring: &RoaringBitmap) -> usize {
if roaring.len() <= THRESHOLD as u64 {
if Self::bitmap_serialize_as_raw_u32s(roaring) {
roaring.len() as usize * size_of::<u32>()
} else {
roaring.serialized_size()
@@ -35,10 +46,7 @@ impl CboRoaringBitmapCodec {
roaring: &RoaringBitmap,
mut writer: W,
) -> io::Result<()> {
if roaring.len() <= THRESHOLD as u64 {
// If the number of items (u32s) to encode is less than or equal to the threshold
// it means that it would weigh the same or less than the RoaringBitmap
// header, so we directly encode them using ByteOrder instead.
if Self::bitmap_serialize_as_raw_u32s(roaring) {
for integer in roaring {
writer.write_u32::<NativeEndian>(integer)?;
}
@@ -51,7 +59,7 @@ impl CboRoaringBitmapCodec {
}
pub fn deserialize_from(mut bytes: &[u8]) -> io::Result<RoaringBitmap> {
if bytes.len() <= THRESHOLD * size_of::<u32>() {
if Self::bytes_deserialize_as_raw_u32s(bytes) {
// If there is threshold or less than threshold integers that can fit into this array
// of bytes it means that we used the ByteOrder codec serializer.
let mut bitmap = RoaringBitmap::new();
@@ -71,7 +79,7 @@ impl CboRoaringBitmapCodec {
other: &RoaringBitmap,
) -> io::Result<RoaringBitmap> {
// See above `deserialize_from` method for implementation details.
if bytes.len() <= THRESHOLD * size_of::<u32>() {
if Self::bytes_deserialize_as_raw_u32s(bytes) {
let mut bitmap = RoaringBitmap::new();
while let Ok(integer) = bytes.read_u32::<NativeEndian>() {
if other.contains(integer) {
@@ -98,7 +106,7 @@ impl CboRoaringBitmapCodec {
let mut vec = Vec::new();
for bytes in slices {
if bytes.as_ref().len() <= THRESHOLD * size_of::<u32>() {
if Self::bytes_deserialize_as_raw_u32s(bytes.as_ref()) {
let mut reader = bytes.as_ref();
while let Ok(integer) = reader.read_u32::<NativeEndian>() {
vec.push(integer);
@@ -112,6 +120,8 @@ impl CboRoaringBitmapCodec {
vec.sort_unstable();
vec.dedup();
// Be careful when modifying this condition,
// the rule must be the same everywhere
if vec.len() <= THRESHOLD {
for integer in vec {
buffer.extend_from_slice(&integer.to_ne_bytes());

View File

@@ -0,0 +1,102 @@
use std::borrow::Cow;
use std::io::{self, ErrorKind};
use heed::BoxedError;
use roaring::RoaringBitmap;
use super::cbo_roaring_bitmap_codec::CboRoaringBitmapCodec;
use super::de_roaring_bitmap_codec::DeRoaringBitmapCodec;
use crate::heed_codec::BytesDecodeOwned;
pub struct DeCboRoaringBitmapCodec;
impl DeCboRoaringBitmapCodec {
pub fn serialized_size_with_tmp_buffer(
bitmap: &RoaringBitmap,
tmp_buffer: &mut Vec<u32>,
) -> usize {
DeRoaringBitmapCodec::serialized_size_with_tmp_buffer(bitmap, tmp_buffer)
}
/// Writes the delta-encoded compressed version of
/// the given roaring bitmap into the provided writer.
pub fn serialize_into<W: io::Write>(bitmap: &RoaringBitmap, writer: W) -> io::Result<()> {
let mut tmp_buffer = Vec::new();
Self::serialize_into_with_tmp_buffer(bitmap, writer, &mut tmp_buffer)
}
/// Same as [Self::serialize_into] but accepts a buffer to avoid allocating one.
///
/// Note that we always serialize the bitmap with the delta-encoded compressed version.
pub fn serialize_into_with_tmp_buffer<W: io::Write>(
bitmap: &RoaringBitmap,
writer: W,
tmp_buffer: &mut Vec<u32>,
) -> io::Result<()> {
// We are stuck with this format because the CboRoaringBitmapCodec decides to write
// raw and unencoded u32s, without a header when there is at most THRESHOLD elements.
if CboRoaringBitmapCodec::bitmap_serialize_as_raw_u32s(bitmap) {
CboRoaringBitmapCodec::serialize_into_writer(bitmap, writer)
} else {
DeRoaringBitmapCodec::serialize_into_with_tmp_buffer(bitmap, writer, tmp_buffer)
}
}
/// Returns the delta-decoded roaring bitmap from the compressed bytes.
pub fn deserialize_from(compressed: &[u8]) -> io::Result<RoaringBitmap> {
let mut tmp_buffer = Vec::new();
Self::deserialize_from_with_tmp_buffer(compressed, &mut tmp_buffer)
}
/// Same as [Self::deserialize_from] but accepts a buffer to avoid allocating one.
///
/// It tries to decode the input by using the delta-decoded version and
/// if it fails, falls back to the CboRoaringBitmap version.
pub fn deserialize_from_with_tmp_buffer(
input: &[u8],
tmp_buffer: &mut Vec<u32>,
) -> io::Result<RoaringBitmap> {
// The input is too short to be a valid delta-decoded bitmap.
// We fall back to the CboRoaringBitmap version with raw u32s.
if CboRoaringBitmapCodec::bytes_deserialize_as_raw_u32s(input) {
return CboRoaringBitmapCodec::deserialize_from(input);
}
match DeRoaringBitmapCodec::deserialize_from_with_tmp_buffer(input, tmp_buffer) {
Ok(bitmap) => Ok(bitmap),
// If the error kind is Other it means that the delta-decoder found
// an invalid magic header. We fall back to the CboRoaringBitmap version.
Err(e) if e.kind() == ErrorKind::Other => {
CboRoaringBitmapCodec::deserialize_from(input)
}
Err(e) => Err(e),
}
}
}
impl heed::BytesDecode<'_> for DeCboRoaringBitmapCodec {
type DItem = RoaringBitmap;
fn bytes_decode(bytes: &[u8]) -> Result<Self::DItem, BoxedError> {
Self::deserialize_from(bytes).map_err(Into::into)
}
}
impl BytesDecodeOwned for DeCboRoaringBitmapCodec {
type DItem = RoaringBitmap;
fn bytes_decode_owned(bytes: &[u8]) -> Result<Self::DItem, BoxedError> {
Self::deserialize_from(bytes).map_err(Into::into)
}
}
impl heed::BytesEncode<'_> for DeCboRoaringBitmapCodec {
type EItem = RoaringBitmap;
fn bytes_encode(item: &Self::EItem) -> Result<Cow<'_, [u8]>, BoxedError> {
// let mut vec = Vec::with_capacity(Self::serialized_size(item));
// Self::serialize_into_vec(item, &mut vec);
// Ok(Cow::Owned(vec))
todo!()
}
}

View File

@@ -0,0 +1,377 @@
use std::io::{self, ErrorKind};
use std::mem::{self, size_of, size_of_val};
use bitpacking::{BitPacker, BitPacker1x, BitPacker4x, BitPacker8x};
use roaring::RoaringBitmap;
/// The magic header for our custom encoding format
const MAGIC_HEADER: u16 = 36869;
pub struct DeRoaringBitmapCodec;
// TODO reintroduce:
// - serialized_size?
// - serialize_into_vec
// - intersection_with_serialized
// - merge_into
// - merge_deladd_into
impl DeRoaringBitmapCodec {
/// Returns the serialized size of the given roaring bitmap with the delta encoding format.
pub fn serialized_size_with_tmp_buffer(
bitmap: &RoaringBitmap,
tmp_buffer: &mut Vec<u32>,
) -> usize {
let mut size = 2; // u16 magic header
let bitpacker8x = BitPacker8x::new();
let bitpacker4x = BitPacker4x::new();
let bitpacker1x = BitPacker1x::new();
// This temporary buffer is used to store each chunk of decompressed u32s.
tmp_buffer.resize(BitPacker8x::BLOCK_LEN, 0u32);
let decompressed = &mut tmp_buffer[..];
let mut buffer_index = 0;
let mut initial = None;
// We initially collect all the integers into a flat buffer of the size
// of the largest bitpacker. We encode them with it until we don't have
// enough of them...
for n in bitmap {
decompressed[buffer_index] = n;
buffer_index += 1;
if buffer_index == BitPacker8x::BLOCK_LEN {
let num_bits = bitpacker8x.num_bits_strictly_sorted(initial, decompressed);
let compressed_len = BitPacker8x::compressed_block_size(num_bits);
size += 1; // u8 chunk header
size += compressed_len; // compressed data length
initial = Some(n);
buffer_index = 0;
}
}
// ...We then switch to a smaller bitpacker to encode the remaining chunks...
let decompressed = &decompressed[..buffer_index];
let mut chunks = decompressed.chunks_exact(BitPacker4x::BLOCK_LEN);
for decompressed in chunks.by_ref() {
let num_bits = bitpacker4x.num_bits_strictly_sorted(initial, decompressed);
let compressed_len = BitPacker4x::compressed_block_size(num_bits);
size += 1; // u8 chunk header
size += compressed_len; // compressed data length
initial = decompressed.iter().last().copied();
}
// ...And so on...
let decompressed = chunks.remainder();
let mut chunks = decompressed.chunks_exact(BitPacker1x::BLOCK_LEN);
for decompressed in chunks.by_ref() {
let num_bits = bitpacker1x.num_bits_strictly_sorted(initial, decompressed);
let compressed_len = BitPacker1x::compressed_block_size(num_bits);
size += 1; // u8 chunk header
size += compressed_len; // compressed data length
initial = decompressed.iter().last().copied();
}
// ...Until we don't have any small enough bitpacker. We put them raw
// at the end of out buffer with a header indicating the matter.
let decompressed = chunks.remainder();
if !decompressed.is_empty() {
size += 1; // u8 chunk header
size += decompressed.len() * mem::size_of::<u32>(); // remaining uncompressed u32s
}
size
}
/// Writes the delta-encoded compressed version of
/// the given roaring bitmap into the provided writer.
pub fn serialize_into<W: io::Write>(bitmap: &RoaringBitmap, writer: W) -> io::Result<()> {
let mut tmp_buffer = Vec::new();
Self::serialize_into_with_tmp_buffer(bitmap, writer, &mut tmp_buffer)
}
/// Same as [Self::serialize_into] but accepts a buffer to avoid allocating one.
pub fn serialize_into_with_tmp_buffer<W: io::Write>(
bitmap: &RoaringBitmap,
mut writer: W,
tmp_buffer: &mut Vec<u32>,
) -> io::Result<()> {
// Insert the magic header
writer.write_all(&MAGIC_HEADER.to_ne_bytes())?;
let bitpacker8x = BitPacker8x::new();
let bitpacker4x = BitPacker4x::new();
let bitpacker1x = BitPacker1x::new();
// This temporary buffer is used to store each chunk of decompressed and
// compressed and delta-encoded u32s. We need room for the decompressed
// u32s coming from the roaring bitmap, the compressed output that can
// be as large as the decompressed u32s, and the chunk header.
tmp_buffer.resize((BitPacker8x::BLOCK_LEN * 2) + 1, 0u32);
let (decompressed, compressed) = tmp_buffer.split_at_mut(BitPacker8x::BLOCK_LEN);
let compressed = bytemuck::cast_slice_mut(compressed);
let mut buffer_index = 0;
let mut initial = None;
// We initially collect all the integers into a flat buffer of the size
// of the largest bitpacker. We encode them with it until we don't have
// enough of them...
for n in bitmap {
decompressed[buffer_index] = n;
buffer_index += 1;
if buffer_index == BitPacker8x::BLOCK_LEN {
let output = encode_with_packer(&bitpacker8x, decompressed, initial, compressed);
writer.write_all(output)?;
initial = Some(n);
buffer_index = 0;
}
}
// ...We then switch to a smaller bitpacker to encode the remaining chunks...
let decompressed = &decompressed[..buffer_index];
let mut chunks = decompressed.chunks_exact(BitPacker4x::BLOCK_LEN);
for decompressed in chunks.by_ref() {
let output = encode_with_packer(&bitpacker4x, decompressed, initial, compressed);
writer.write_all(output)?;
initial = decompressed.iter().last().copied();
}
// ...And so on...
let decompressed = chunks.remainder();
let mut chunks = decompressed.chunks_exact(BitPacker1x::BLOCK_LEN);
for decompressed in chunks.by_ref() {
let output = encode_with_packer(&bitpacker1x, decompressed, initial, compressed);
writer.write_all(output)?;
initial = decompressed.iter().last().copied();
}
// ...Until we don't have any small enough bitpacker. We put them raw
// at the end of out buffer with a header indicating the matter.
let decompressed = chunks.remainder();
if !decompressed.is_empty() {
let header = encode_chunk_header(BitPackerLevel::None, u32::BITS as u8);
// Note: Not convinced about the performance of writing a single
// byte followed by a larger write. However, we will use this
// codec with a BufWriter or directly with a Vec of bytes.
writer.write_all(&[header])?;
writer.write_all(bytemuck::cast_slice(decompressed))?;
}
Ok(())
}
/// Returns the delta-decoded roaring bitmap from the compressed bytes.
pub fn deserialize_from(compressed: &[u8]) -> io::Result<RoaringBitmap> {
let mut tmp_buffer = Vec::new();
Self::deserialize_from_with_tmp_buffer(compressed, &mut tmp_buffer)
}
/// Same as [Self::deserialize_from] but accepts a buffer to avoid allocating one.
pub fn deserialize_from_with_tmp_buffer(
input: &[u8],
tmp_buffer: &mut Vec<u32>,
) -> io::Result<RoaringBitmap> {
let Some((header, mut compressed)) = input.split_at_checked(size_of_val(&MAGIC_HEADER))
else {
return Err(io::Error::new(ErrorKind::UnexpectedEof, "expecting a two-bytes header"));
};
// Safety: This unwrap cannot happen as the header buffer is the right size
let header = u16::from_ne_bytes(header.try_into().unwrap());
if header != MAGIC_HEADER {
return Err(io::Error::other("invalid header value"));
}
let bitpacker8x = BitPacker8x::new();
let bitpacker4x = BitPacker4x::new();
let bitpacker1x = BitPacker1x::new();
let mut bitmap = RoaringBitmap::new();
tmp_buffer.resize(BitPacker8x::BLOCK_LEN, 0u32);
let decompressed = &mut tmp_buffer[..];
let mut initial = None;
while let Some((&chunk_header, encoded)) = compressed.split_first() {
let (level, num_bits) = decode_chunk_header(chunk_header);
let (bytes_read, decompressed) = match level {
BitPackerLevel::None => {
if num_bits != u32::BITS as u8 {
return Err(io::Error::new(
ErrorKind::InvalidData,
"invalid number of bits to encode non-compressed u32s",
));
}
let chunks = encoded.chunks_exact(size_of::<u32>());
if !chunks.remainder().is_empty() {
return Err(io::Error::new(
io::ErrorKind::InvalidData,
"expecting last chunk to be a multiple of the size of an u32",
));
}
let integers = chunks
// safety: This unwrap cannot happen as
// the size of u32 is set correctly.
.map(|b| b.try_into().unwrap())
.map(u32::from_ne_bytes);
bitmap
.append(integers)
.map_err(|e| io::Error::new(ErrorKind::InvalidData, e))?;
// This is basically always the last chunk that exists in
// this delta-encoded format as the raw u32s are appended
// when there is not enough of them to fit in a bitpacker.
break;
}
BitPackerLevel::BitPacker1x => {
decode_with_packer(&bitpacker1x, decompressed, initial, encoded, num_bits)
}
BitPackerLevel::BitPacker4x => {
decode_with_packer(&bitpacker4x, decompressed, initial, encoded, num_bits)
}
BitPackerLevel::BitPacker8x => {
decode_with_packer(&bitpacker8x, decompressed, initial, encoded, num_bits)
}
};
initial = decompressed.iter().last().copied();
// TODO investigate perf
// Safety: Bitpackers cannot output unsorter integers when
// used with the compress_strictly_sorted function.
bitmap.append(decompressed.iter().copied()).unwrap();
// What the delta-decoding read plus the chunk header size
compressed = &compressed[bytes_read + 1..];
}
Ok(bitmap)
}
}
/// Takes a strickly sorted list of u32s and outputs delta-encoded
/// bytes with a chunk header. We expect the output buffer to be
/// at least BLOCK_LEN + 1.
fn encode_with_packer<'c, B: BitPackerExt>(
bitpacker: &B,
decompressed: &[u32],
initial: Option<u32>,
output: &'c mut [u8],
) -> &'c [u8] {
let num_bits = bitpacker.num_bits_strictly_sorted(initial, decompressed);
let compressed_len = B::compressed_block_size(num_bits);
let chunk_header = encode_chunk_header(B::level(), num_bits);
let buffer = &mut output[..compressed_len + 1];
// Safety: The buffer is at least one byte
let (header_in_buffer, encoded) = buffer.split_first_mut().unwrap();
*header_in_buffer = chunk_header;
bitpacker.compress_strictly_sorted(initial, decompressed, encoded, num_bits);
buffer
}
/// Returns the number of bytes read and the decoded unsigned integers.
fn decode_with_packer<'d, B: BitPacker>(
bitpacker: &B,
decompressed: &'d mut [u32],
initial: Option<u32>,
compressed: &[u8],
num_bits: u8,
) -> (usize, &'d [u32]) {
let decompressed = &mut decompressed[..B::BLOCK_LEN];
let read = bitpacker.decompress_strictly_sorted(initial, compressed, decompressed, num_bits);
(read, decompressed)
}
/// An identifier for the bitpacker to be able
/// to correctly decode the compressed integers.
#[derive(Debug, PartialEq, Eq)]
#[repr(u8)]
enum BitPackerLevel {
/// The remaining bytes are raw little endian encoded u32s.
None,
/// The remaining bits are encoded using a `BitPacker1x`.
BitPacker1x,
/// The remaining bits are encoded using a `BitPacker4x`.
BitPacker4x,
/// The remaining bits are encoded using a `BitPacker8x`.
BitPacker8x,
}
/// Returns the chunk header based on the bitpacker level
/// and the number of bits to encode the list of integers.
fn encode_chunk_header(level: BitPackerLevel, num_bits: u8) -> u8 {
debug_assert!(num_bits as u32 <= 2_u32.pow(6));
let level = level as u8;
debug_assert!(level <= 3);
num_bits | (level << 6)
}
/// Decodes the chunk header and output the bitpacker level
/// and the number of bits to decode the following bytes.
fn decode_chunk_header(data: u8) -> (BitPackerLevel, u8) {
let num_bits = data & 0b00111111;
let level = match data >> 6 {
0 => BitPackerLevel::None,
1 => BitPackerLevel::BitPacker1x,
2 => BitPackerLevel::BitPacker4x,
3 => BitPackerLevel::BitPacker8x,
invalid => panic!("Invalid bitpacker level: {invalid}"),
};
debug_assert!(num_bits as u32 <= 2_u32.pow(6));
(level, num_bits)
}
/// A simple helper trait to get the BitPackerLevel
/// and correctly generate the chunk header.
trait BitPackerExt: BitPacker {
/// Returns the level of the bitpacker: an identifier to be
/// able to decode the numbers with the right bitpacker.
fn level() -> BitPackerLevel;
}
impl BitPackerExt for BitPacker8x {
fn level() -> BitPackerLevel {
BitPackerLevel::BitPacker8x
}
}
impl BitPackerExt for BitPacker4x {
fn level() -> BitPackerLevel {
BitPackerLevel::BitPacker4x
}
}
impl BitPackerExt for BitPacker1x {
fn level() -> BitPackerLevel {
BitPackerLevel::BitPacker1x
}
}
#[cfg(test)]
mod tests {
use quickcheck::quickcheck;
use roaring::RoaringBitmap;
use super::DeRoaringBitmapCodec;
quickcheck! {
fn qc_random(xs: Vec<u32>) -> bool {
let bitmap = RoaringBitmap::from_iter(xs);
let mut compressed = Vec::new();
DeRoaringBitmapCodec::serialize_into(&bitmap, &mut compressed).unwrap();
let decompressed = DeRoaringBitmapCodec::deserialize_from(&compressed[..]).unwrap();
decompressed == bitmap
}
}
quickcheck! {
fn qc_random_check_serialized_size(xs: Vec<u32>) -> bool {
let bitmap = RoaringBitmap::from_iter(xs);
let mut compressed = Vec::new();
let mut tmp_buffer = Vec::new();
DeRoaringBitmapCodec::serialize_into(&bitmap, &mut compressed).unwrap();
let expected_len = DeRoaringBitmapCodec::serialized_size_with_tmp_buffer(&bitmap, &mut tmp_buffer);
compressed.len() == expected_len
}
}
}

View File

@@ -1,7 +1,10 @@
mod bo_roaring_bitmap_codec;
pub mod cbo_roaring_bitmap_codec;
pub mod de_cbo_roaring_bitmap_codec;
mod de_roaring_bitmap_codec;
mod roaring_bitmap_codec;
pub use self::bo_roaring_bitmap_codec::BoRoaringBitmapCodec;
pub use self::cbo_roaring_bitmap_codec::CboRoaringBitmapCodec;
pub use self::de_cbo_roaring_bitmap_codec::DeCboRoaringBitmapCodec;
pub use self::roaring_bitmap_codec::RoaringBitmapCodec;

View File

@@ -44,7 +44,6 @@ const UPGRADE_FUNCTIONS: &[&dyn UpgradeIndex] = &[
&ToTargetNoOp { target: (1, 24, 0) },
&ToTargetNoOp { target: (1, 25, 0) },
&ToTargetNoOp { target: (1, 26, 0) },
&ToTargetNoOp { target: (1, 27, 0) },
// This is the last upgrade function, it will be called when the index is up to date.
// any other upgrade function should be added before this one.
&ToCurrentNoOp {},
@@ -82,7 +81,6 @@ const fn start(from: (u32, u32, u32)) -> Option<usize> {
(1, 24, _) => function_index!(14),
(1, 25, _) => function_index!(15),
(1, 26, _) => function_index!(16),
(1, 27, _) => function_index!(17),
// We deliberately don't add a placeholder with (VERSION_MAJOR, VERSION_MINOR, VERSION_PATCH) here to force manually
// considering dumpless upgrade.
(_major, _minor, _patch) => return None,